Xavier Velez — accepted AI-conference papers

2024

Deferred NAM: Low-latency Top-K Context Injection via Deferred Context Encoding for Non-Streaming ASR

Zelin Wu, Gan Song, Christopher Li, Pat Rondon, Zhong Meng, Xavier Velez +6

NAACL 2024industry

Contextual biasing enables speech recognizers to transcribe important phrases in the speaker’s context, such as contact names, even if they are rare in, or absent from, the training data. Attention-based biasing is a leading approach which allows for full end-to-end cotraining of the recognizer and…

Cited by 2 Source ↗PDF ↗Scholar ↗

2021

Improving Entity Recall in Automatic Speech Recognition with Neural Embeddings

Christopher Li, Pat Rondon, Diamantino Caseiro, Leonid Velikovich, Xavier Velez, Petar S. Aleksic

ICASSP 2021accepted

Automatic speech recognition (ASR) systems often have difficulty recognizing long-tail entities such as contact names and local restaurant names, which usually do not occur, or occur infrequently, in the system’s training data. In this work, we present a method which uses learned text embeddings and…

Cited by 0 Source ↗Scholar ↗